A Novel Approach to the Unsupervised Update of Land-Cover Maps by Classification of Time Series of Multispectral Images

Abstract

This paper presents an unsupervised approach that extracts reliable labeled units from outdated maps to update them using time series (TS) of recent multispectral (MS) images. The method assumes that: (1) the source of the map is unknown and may be different from remote sensing (RS) data; (2) no ground truth is available; (3) the map is provided at polygon level, where the polygon label represents the dominant class; and (4) the map legend can be converted into a set of classes discriminable with the TS of images (i.e., no land-use classes that require manual analysis are considered). First, the outdated map is adapted to the spatial and spectral properties of the MS images. Then, the method identifies reliable labeled units in an unsupervised way by a two-step procedure: (1) a clustering analysis performed at polygon level to detect samples correctly associated to their labels, and (2) a consistency analysis to discard polygons far from the distribution of the related land-cover class (i.e., having high probability of being mislabeled). Finally, the map is updated by classifying the recent TS of MS image with an ensemble of classifiers trained using only the reference data derived from the map. The experimental results obtained updating the 2012 Corine Land Cover (CLC) and the GlobLand30 in Trentino Alto Adige (Italy) achieved 93.2% and 93.3% overall accuracy (OA) on the validation data set. The method increased the OA up to 18% and 11.5% with respect to the reference methods on the 2012 CLC and the GlobLand30, respectively.

Bigearthnet: A Large-Scale Benchmark Archive for Remote Sensing Image Understanding

“…The classes maintained are thematically homogeneous and largely related to land cover, such as Broad-leaved forest and Beaches, dunes, sands. Complex cultivation patterns [23] and Land principally occupied by agriculture, with significant areas of natural vegetation [22]. The goal is to investigate the ability of DL models to learn from spatial patterns that express semantic classes.…”

Toward a Yearly Country-Scale CORINE Land-Cover Map without Using Images: A Map Translation Approach

“…Other cases are far more challenging and are poorly addressed by semantic methods [18,26,27]. Simple solutions rely on expert knowledge [28] and are hardly generalizable. When very specific classes are targeted, remote sensing data are often integrated to bring additional constraints [29].…”

A Novel Sample Selection Method for Impervious Surface Area Mapping Using JL1-3B Nighttime Light and Sentinel-2 Imagery

“…However, any other clustering algorithm can be used in this case. Next, the optimal value of K was identified by Calinski Harabasz (CH) index [43], [44]. The index for n data points and K clusters is computed as follows:…”

“…Where the n k is the number of points in cluster k, N is the number of entire data, z k is the centroid of points in cluster and z is the center of the entire data set [44]. Then, the Jeffries-Matusita (JM) distance was used to distinguish the separability between subclasses [45], [46].…”